Discovery of liquid crystalline polymers with high thermal conductivity using machine learning

Abstract Next-generation power electronics require efficient heat dissipation management, and molecular design guidelines are needed to develop polymers with high thermal conductivity. Polymer materials have considerably lower thermal conductivity than metals and ceramics due to phonon scattering in...

Full description

Saved in:
Bibliographic Details
Main Authors: Hayato Maeda, Stephen Wu, Rika Marui, Erina Yoshida, Kan Hatakeyama-Sato, Yuta Nabae, Shiori Nakagawa, Meguya Ryu, Ryohei Ishige, Yoh Noguchi, Yoshihiro Hayashi, Masashi Ishii, Isao Kuwajima, Felix Jiang, Xuan Thang Vu, Sven Ingebrandt, Masatoshi Tokita, Junko Morikawa, Ryo Yoshida, Teruaki Hayakawa
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:npj Computational Materials
Online Access:https://doi.org/10.1038/s41524-025-01671-w
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849334417954177024
author Hayato Maeda
Stephen Wu
Rika Marui
Erina Yoshida
Kan Hatakeyama-Sato
Yuta Nabae
Shiori Nakagawa
Meguya Ryu
Ryohei Ishige
Yoh Noguchi
Yoshihiro Hayashi
Masashi Ishii
Isao Kuwajima
Felix Jiang
Xuan Thang Vu
Sven Ingebrandt
Masatoshi Tokita
Junko Morikawa
Ryo Yoshida
Teruaki Hayakawa
author_facet Hayato Maeda
Stephen Wu
Rika Marui
Erina Yoshida
Kan Hatakeyama-Sato
Yuta Nabae
Shiori Nakagawa
Meguya Ryu
Ryohei Ishige
Yoh Noguchi
Yoshihiro Hayashi
Masashi Ishii
Isao Kuwajima
Felix Jiang
Xuan Thang Vu
Sven Ingebrandt
Masatoshi Tokita
Junko Morikawa
Ryo Yoshida
Teruaki Hayakawa
author_sort Hayato Maeda
collection DOAJ
description Abstract Next-generation power electronics require efficient heat dissipation management, and molecular design guidelines are needed to develop polymers with high thermal conductivity. Polymer materials have considerably lower thermal conductivity than metals and ceramics due to phonon scattering in the amorphous region. The spontaneous orientation of the molecular chains of liquid crystalline polymers could potentially give rise to high thermal conductivity, but the molecular design of such polymers remains largely empirical. In this study, we developed a machine learning model that predicts with more than 96% accuracy whether liquid crystalline states will form based on the chemical structure of the polymer. By exploring the inverse mapping of this model, we identified a comprehensive set of chemical structures for liquid crystalline polyimides. The polymers were then experimentally synthesized, and the results confirmed that they form liquid crystalline phases, with all polymers exhibiting calculated thermal conductivities within the range of 0.722–1.26 W m−1 K−1.
format Article
id doaj-art-b097e997be284320b9dd2ebdb679799d
institution Kabale University
issn 2057-3960
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series npj Computational Materials
spelling doaj-art-b097e997be284320b9dd2ebdb679799d2025-08-20T03:45:34ZengNature Portfolionpj Computational Materials2057-39602025-07-011111910.1038/s41524-025-01671-wDiscovery of liquid crystalline polymers with high thermal conductivity using machine learningHayato Maeda0Stephen Wu1Rika Marui2Erina Yoshida3Kan Hatakeyama-Sato4Yuta Nabae5Shiori Nakagawa6Meguya Ryu7Ryohei Ishige8Yoh Noguchi9Yoshihiro Hayashi10Masashi Ishii11Isao Kuwajima12Felix Jiang13Xuan Thang Vu14Sven Ingebrandt15Masatoshi Tokita16Junko Morikawa17Ryo Yoshida18Teruaki Hayakawa19School of Materials and Chemical Technology, Institute of Science TokyoThe Institute of Statistical Mathematics, Research Organization of Information and SystemsSchool of Materials and Chemical Technology, Institute of Science TokyoSchool of Materials and Chemical Technology, Institute of Science TokyoSchool of Materials and Chemical Technology, Institute of Science TokyoSchool of Materials and Chemical Technology, Institute of Science TokyoSchool of Materials and Chemical Technology, Institute of Science TokyoSchool of Materials and Chemical Technology, Institute of Science TokyoSchool of Materials and Chemical Technology, Institute of Science TokyoThe Institute of Statistical Mathematics, Research Organization of Information and SystemsThe Institute of Statistical Mathematics, Research Organization of Information and SystemsNational Institute for Materials ScienceNational Institute for Materials ScienceInstitute of Materials in Electrical Engineering 1, RWTH Aachen UniversityInstitute of Materials in Electrical Engineering 1, RWTH Aachen UniversityInstitute of Materials in Electrical Engineering 1, RWTH Aachen UniversitySchool of Materials and Chemical Technology, Institute of Science TokyoSchool of Materials and Chemical Technology, Institute of Science TokyoThe Institute of Statistical Mathematics, Research Organization of Information and SystemsSchool of Materials and Chemical Technology, Institute of Science TokyoAbstract Next-generation power electronics require efficient heat dissipation management, and molecular design guidelines are needed to develop polymers with high thermal conductivity. Polymer materials have considerably lower thermal conductivity than metals and ceramics due to phonon scattering in the amorphous region. The spontaneous orientation of the molecular chains of liquid crystalline polymers could potentially give rise to high thermal conductivity, but the molecular design of such polymers remains largely empirical. In this study, we developed a machine learning model that predicts with more than 96% accuracy whether liquid crystalline states will form based on the chemical structure of the polymer. By exploring the inverse mapping of this model, we identified a comprehensive set of chemical structures for liquid crystalline polyimides. The polymers were then experimentally synthesized, and the results confirmed that they form liquid crystalline phases, with all polymers exhibiting calculated thermal conductivities within the range of 0.722–1.26 W m−1 K−1.https://doi.org/10.1038/s41524-025-01671-w
spellingShingle Hayato Maeda
Stephen Wu
Rika Marui
Erina Yoshida
Kan Hatakeyama-Sato
Yuta Nabae
Shiori Nakagawa
Meguya Ryu
Ryohei Ishige
Yoh Noguchi
Yoshihiro Hayashi
Masashi Ishii
Isao Kuwajima
Felix Jiang
Xuan Thang Vu
Sven Ingebrandt
Masatoshi Tokita
Junko Morikawa
Ryo Yoshida
Teruaki Hayakawa
Discovery of liquid crystalline polymers with high thermal conductivity using machine learning
npj Computational Materials
title Discovery of liquid crystalline polymers with high thermal conductivity using machine learning
title_full Discovery of liquid crystalline polymers with high thermal conductivity using machine learning
title_fullStr Discovery of liquid crystalline polymers with high thermal conductivity using machine learning
title_full_unstemmed Discovery of liquid crystalline polymers with high thermal conductivity using machine learning
title_short Discovery of liquid crystalline polymers with high thermal conductivity using machine learning
title_sort discovery of liquid crystalline polymers with high thermal conductivity using machine learning
url https://doi.org/10.1038/s41524-025-01671-w
work_keys_str_mv AT hayatomaeda discoveryofliquidcrystallinepolymerswithhighthermalconductivityusingmachinelearning
AT stephenwu discoveryofliquidcrystallinepolymerswithhighthermalconductivityusingmachinelearning
AT rikamarui discoveryofliquidcrystallinepolymerswithhighthermalconductivityusingmachinelearning
AT erinayoshida discoveryofliquidcrystallinepolymerswithhighthermalconductivityusingmachinelearning
AT kanhatakeyamasato discoveryofliquidcrystallinepolymerswithhighthermalconductivityusingmachinelearning
AT yutanabae discoveryofliquidcrystallinepolymerswithhighthermalconductivityusingmachinelearning
AT shiorinakagawa discoveryofliquidcrystallinepolymerswithhighthermalconductivityusingmachinelearning
AT meguyaryu discoveryofliquidcrystallinepolymerswithhighthermalconductivityusingmachinelearning
AT ryoheiishige discoveryofliquidcrystallinepolymerswithhighthermalconductivityusingmachinelearning
AT yohnoguchi discoveryofliquidcrystallinepolymerswithhighthermalconductivityusingmachinelearning
AT yoshihirohayashi discoveryofliquidcrystallinepolymerswithhighthermalconductivityusingmachinelearning
AT masashiishii discoveryofliquidcrystallinepolymerswithhighthermalconductivityusingmachinelearning
AT isaokuwajima discoveryofliquidcrystallinepolymerswithhighthermalconductivityusingmachinelearning
AT felixjiang discoveryofliquidcrystallinepolymerswithhighthermalconductivityusingmachinelearning
AT xuanthangvu discoveryofliquidcrystallinepolymerswithhighthermalconductivityusingmachinelearning
AT sveningebrandt discoveryofliquidcrystallinepolymerswithhighthermalconductivityusingmachinelearning
AT masatoshitokita discoveryofliquidcrystallinepolymerswithhighthermalconductivityusingmachinelearning
AT junkomorikawa discoveryofliquidcrystallinepolymerswithhighthermalconductivityusingmachinelearning
AT ryoyoshida discoveryofliquidcrystallinepolymerswithhighthermalconductivityusingmachinelearning
AT teruakihayakawa discoveryofliquidcrystallinepolymerswithhighthermalconductivityusingmachinelearning